{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OZXYNJGRRCOOGV6NUDNGJKOMT3","short_pith_number":"pith:OZXYNJGR","canonical_record":{"source":{"id":"2305.08350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T05:07:45Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c7577b187fcc7ef99e5044b6a8b581eecca9306baa504427950bba8112f47062","abstract_canon_sha256":"d5f3666425100f8a39d0cd0194519f156c0d46fa14208be8dd923fd5fa5f7f36"},"schema_version":"1.0"},"canonical_sha256":"766f86a4d1889ce357cda0da64a9cc9ee5d581d17bbd5c5fa36effa11157cdf9","source":{"kind":"arxiv","id":"2305.08350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08350","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08350v1","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08350","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"OZXYNJGRRCOO","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"OZXYNJGRRCOOGV6N","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"OZXYNJGR","created_at":"2026-07-05T06:10:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OZXYNJGRRCOOGV6NUDNGJKOMT3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T05:07:45Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c7577b187fcc7ef99e5044b6a8b581eecca9306baa504427950bba8112f47062","abstract_canon_sha256":"d5f3666425100f8a39d0cd0194519f156c0d46fa14208be8dd923fd5fa5f7f36"},"schema_version":"1.0"},"canonical_sha256":"766f86a4d1889ce357cda0da64a9cc9ee5d581d17bbd5c5fa36effa11157cdf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:00.476047Z","signature_b64":"1Fm1xLr3gU3FBbbeYU2IcqQpASDeNR114kbKz3bWfFDoCJ0FSUY/H5A527/86tkPQjlw9ZLpcbCt0OTZGDk5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"766f86a4d1889ce357cda0da64a9cc9ee5d581d17bbd5c5fa36effa11157cdf9","last_reissued_at":"2026-07-05T06:10:00.475596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:00.475596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08350","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zitxLailqIaSaSNGfPkuqEbbqGCoziWhAQsHrB51u07lpj6WBlBwjBwESDpH6LjwPNZgWV5/tVBvY28THci+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:39:22.884721Z"},"content_sha256":"41e023452b63a07bff482274d4157b3051d08cfd179d7ab4f745d5d5aa7da307","schema_version":"1.0","event_id":"sha256:41e023452b63a07bff482274d4157b3051d08cfd179d7ab4f745d5d5aa7da307"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OZXYNJGRRCOOGV6NUDNGJKOMT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiafan He, Quanquan Gu, Yue Wu","submitted_at":"2023-05-15T05:07:45Z","abstract_excerpt":"Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation. However, all these works only provide regret or sample complexity guarantees. It is still an open question if one can achieve stronger performance guarantees, i.e., the uniform probably approximate correctness (Uniform-PAC) guarantee that can imply both a sub-linear regret bound and a polynomial sample complexity for any target learning accuracy. We study this problem by proposing algorithms for both nonlinear bandits and model-based episodic RL using the general function class with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08350","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.08350/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wv5e+Cyz45GaAPYYL3kGfi9PK3CZqrwl1wQkO7lv04I0zmzThO05PoW9zYSI/uy9vlQjf1DfCI5Ej8kthWESDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:39:22.885103Z"},"content_sha256":"4ea815357279dcb3dc5c216381d90a7094aed4e6b447f579778799c172df048b","schema_version":"1.0","event_id":"sha256:4ea815357279dcb3dc5c216381d90a7094aed4e6b447f579778799c172df048b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/bundle.json","state_url":"https://pith.science/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:39:22Z","links":{"resolver":"https://pith.science/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3","bundle":"https://pith.science/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/bundle.json","state":"https://pith.science/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZXYNJGRRCOOGV6NUDNGJKOMT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OZXYNJGRRCOOGV6NUDNGJKOMT3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d5f3666425100f8a39d0cd0194519f156c0d46fa14208be8dd923fd5fa5f7f36","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T05:07:45Z","title_canon_sha256":"c7577b187fcc7ef99e5044b6a8b581eecca9306baa504427950bba8112f47062"},"schema_version":"1.0","source":{"id":"2305.08350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08350","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08350v1","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08350","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"OZXYNJGRRCOO","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"OZXYNJGRRCOOGV6N","created_at":"2026-07-05T06:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"OZXYNJGR","created_at":"2026-07-05T06:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:4ea815357279dcb3dc5c216381d90a7094aed4e6b447f579778799c172df048b","target":"graph","created_at":"2026-07-05T06:10:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.08350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation. However, all these works only provide regret or sample complexity guarantees. It is still an open question if one can achieve stronger performance guarantees, i.e., the uniform probably approximate correctness (Uniform-PAC) guarantee that can imply both a sub-linear regret bound and a polynomial sample complexity for any target learning accuracy. We study this problem by proposing algorithms for both nonlinear bandits and model-based episodic RL using the general function class with","authors_text":"Jiafan He, Quanquan Gu, Yue Wu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T05:07:45Z","title":"Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08350","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41e023452b63a07bff482274d4157b3051d08cfd179d7ab4f745d5d5aa7da307","target":"record","created_at":"2026-07-05T06:10:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d5f3666425100f8a39d0cd0194519f156c0d46fa14208be8dd923fd5fa5f7f36","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T05:07:45Z","title_canon_sha256":"c7577b187fcc7ef99e5044b6a8b581eecca9306baa504427950bba8112f47062"},"schema_version":"1.0","source":{"id":"2305.08350","kind":"arxiv","version":1}},"canonical_sha256":"766f86a4d1889ce357cda0da64a9cc9ee5d581d17bbd5c5fa36effa11157cdf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"766f86a4d1889ce357cda0da64a9cc9ee5d581d17bbd5c5fa36effa11157cdf9","first_computed_at":"2026-07-05T06:10:00.475596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:00.475596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Fm1xLr3gU3FBbbeYU2IcqQpASDeNR114kbKz3bWfFDoCJ0FSUY/H5A527/86tkPQjlw9ZLpcbCt0OTZGDk5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:00.476047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e023452b63a07bff482274d4157b3051d08cfd179d7ab4f745d5d5aa7da307","sha256:4ea815357279dcb3dc5c216381d90a7094aed4e6b447f579778799c172df048b"],"state_sha256":"01035d796a5b7b3e351ef5de5f9d2513803fea0e0e968f3a904f6d4e05495bf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1GZMzcXyOsOm+20cE3Tp/92K71oJG4pGeaG3XBNUc7k67xYFtjBXGlvRp0OTbGQoIeyYBmDNVQ4h4eDiCC+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:39:22.887472Z","bundle_sha256":"f2420a01ad73c87f84256d95686355d9d6e2cb173b81059f30c1977b40aed736"}}